Learn the critical vocabulary of AI evaluation, safety mechanisms, and responsible development. This deck covers metrics like BLEU and ROUGE, safety concepts like red teaming and guardrails, and ethics terms like bias, fairness, and explainability — essential knowledge for building trustworthy AI systems.
25 cards
←→ Navigate·Space Flip·Enter Submit·Swipe on mobile
/
Front
Click or press Space to flip
Back
Term
Definition
What term matches this definition?
Correct!
Incorrect
Your answer:
Correct:
You got out of correct
Correct
Incorrect
Total
+
Finding these flashcards helpful?
Your support helps me create more free learning resources.